Volume 54 - Article 23 | Pages 719–762  

Probabilistic population forecasts for small regions

By Julius Goes, Henriette Engelhardt

Abstract

Background: Age-specific population forecasts for small areas or subnational regions are a valuable tool for local governments. However, typical population projection methods based on the cohort-component approach are difficult to apply on a smaller subnational scale.

Objective: We introduce Bayesian methods suitable for obtaining reliable age-specific population forecasts for small regions using the cohort-component method.

Methods: Our approach improves fertility forecasting by extending the Lee–Carter model with an age-region interaction term. We propose to forecast net-migration counts using skewed error terms, and introduce a Dirichlet regression to model migration age patterns as well as age proportions of fertility.

Results: We run our model to produce age-specific population forecasts for a set of 13 heterogeneous regions in Bavaria, Germany. We compare our method with other standard approaches and find that it produces superior out-of-sample forecasts according to both point measures and scoring rules.

Conclusions: The findings suggest that the proposed Bayesian methods offer good predictive accuracy and are suitable in obtaining precise forecasts of age-specific population for smaller geo-graphical regions.

Contribution: We introduce a new method for the probabilistic projection of subnational population that works well and outperforms other current methods.

Author’s Affiliation

• Julius Goes - Universität Bamberg, Germany EMAIL
• Henriette Engelhardt - Otto-Friedrich-Universität Bamberg, Germany EMAIL

Other articles by the same author/authors in Demographic Research

Family inequality: On the changing educational gradient of family patterns in Western Germany
Volume 48 - Article 20

On the age-specific correlation between fertility and female employment: Heterogeneity over space and time in OECD countries
Volume 32 - Article 23

Does fertility decrease household consumption?: An analysis of poverty dynamics and fertility in Indonesia
Volume 20 - Article 26

Austria: Persistent low fertility since the mid-1980s
Volume 19 - Article 12

On the tempo and quantum of first marriages in Austria, Germany, and Switzerland: Changes in mean age and variance
Volume 10 - Article 9

Pathways to stepfamily formation in Europe: Results from the FFS
Volume 8 - Article 5

Differences in Family Policies and the Intergenerational Transmission of Divorce: A Comparison between the former East and West Germany
Volume 6 - Article 11

Similar articles in Demographic Research

Preparing local area population forecasts using a bi-regional cohort-component model without the need for local migration data
Volume 46 - Article 32    | Keywords: cohort-component model, local area, population forecasting, synthetic migration

Probabilistic forecasting of maximum human lifespan by 2100 using Bayesian population projections
Volume 44 - Article 52    | Keywords: Bayesian population projections, human lifespan, population forecasting, supercentenarians

Subnational population forecasts: Do users want to know about uncertainty?
Volume 41 - Article 13    | Keywords: Australia, communication, forecast errors, forecast interval, population forecasting, science, uncertainty

Integrating uncertainty in time series population forecasts: An illustration using a simple projection model
Volume 29 - Article 43    | Keywords: Bayesian approach, England, model averaging, population forecasting, Wales

Estimates of Age-Specific Reductions in HIV Prevalence in Uganda: Bayesian Melding Estimation and Probabilistic Population Forecast with an HIV-enabled Cohort Component Projection Model
Volume 27 - Article 26    | Keywords: Africa, Bayesian melding, cohort-component method, estimation, forecast, HIV/AIDS, IMIS, incidence, prevalence, Tanzania, Uganda